© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 138473
    Prev
    Next
    INDEX
    Explanations

    code fragments and comments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Treasure
    0.49
     middle
    0.47
    ↵
    0.47
     Th
    0.47
     Find
    0.46
     Dep
    0.44
     Calle
    0.44
     Grove
    0.43
     Entre
    0.42
     Hide
    0.42
    POSITIVE LOGITS
    CONFLICT
    0.46
    CMake
    0.46
    вью
    0.46
    ੌਰ
    0.45
    сия
    0.45
    τ
    0.44
     ভিত্ত
    0.44
    mlabeledtr
    0.44
     gesam
    0.43
    サイズの
    0.43
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.